extract_todos
Scan source files for TODO/FIXME/HACK/BUG/XXX/NOTE comments and create tasks from them. Deduplicates on re-runs.
This record as markdown: /tools/todos/extract-todos.md
What extract_todos does on Todos
AI agents use extract_todos to create or update resources in Todos, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
Why extract_todos is rated Medium
The tool reads source files (a Read operation) but its primary effect is creating new tasks from discovered comments. Creating tasks is a Write operation. Deduplication reduces but does not eliminate the risk of spurious task creation if run on unexpected files. Severity is medium because misuse could flood the task system with unwanted tasks, but effects are reversible.
From the tool's definition 'create tasks from them' — the tool scans source files and writes new task records into the task management system
Attacks that exploit this kind of access
The rule that runs extract_todos safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Todos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For extract_todos, this is the rule to start with:
extract_todos stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Todos, apply this rule, and every extract_todos call is checked against it from then on.
Questions about extract_todos
Scan source files for TODO/FIXME/HACK/BUG/XXX/NOTE comments and create tasks from them. Deduplicates on re-runs. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for extract_todos: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Todos. Nothing to install.
extract_todos is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the extract_todos rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for extract_todos. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
extract_todos is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Todos, and thousands of servers like it.
This server
Across the catalogue